Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rmk/linux

Pull ARM updates from Russell King:

- add dev_is_amba() function to allow conversions during the next cycle

- improve PREEMPT_RT performance with VFP

- KASAN fixes for vmap stack

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rmk/linux:
ARM: 9431/1: mm: Pair atomic_set_release() with _read_acquire()
ARM: 9430/1: entry: Do a dummy read from VMAP shadow
ARM: 9429/1: ioremap: Sync PGDs for VMALLOC shadow
ARM: 9426/1: vfp: Move sending signals outside of vfp_state_hold()ed section.
ARM: 9425/1: vfp: Use vfp_state_hold() in vfp_support_entry().
ARM: 9424/1: vfp: Use vfp_state_hold() in vfp_sync_hwstate().
ARM: 9423/1: vfp: Provide vfp_state_hold() for VFP locking.
ARM: 9415/1: amba: Add dev_is_amba() function and export it for modules

arch/arm/kernel/entry-armv.S

···
 #include <asm/tls.h>
 #include <asm/system_info.h>
 #include <asm/uaccess-asm.h>
+#include <asm/kasan_def.h>
 
 #include "entry-header.S"
 #include <asm/probes.h>
···
 	@ entries covering the vmalloc region.
 	@
 	ldr	r2, [ip]
+#ifdef CONFIG_KASAN_VMALLOC
+	@ Also dummy read from the KASAN shadow memory for the new stack if we
+	@ are using KASAN
+	mov_l	r2, KASAN_SHADOW_OFFSET
+	add	r2, r2, ip, lsr #KASAN_SHADOW_SCALE_SHIFT
+	ldr	r2, [r2]
+#endif
 #endif
 
 	@ When CONFIG_THREAD_INFO_IN_TASK=n, the update of SP itself is what

arch/arm/mm/ioremap.c

···
  */
 #include <linux/module.h>
 #include <linux/errno.h>
+#include <linux/kasan.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/io.h>
···
 }
 EXPORT_SYMBOL(ioremap_page);
 
+#ifdef CONFIG_KASAN
+static unsigned long arm_kasan_mem_to_shadow(unsigned long addr)
+{
+	return (unsigned long)kasan_mem_to_shadow((void *)addr);
+}
+#else
+static unsigned long arm_kasan_mem_to_shadow(unsigned long addr)
+{
+	return 0;
+}
+#endif
+
+static void memcpy_pgd(struct mm_struct *mm, unsigned long start,
+		       unsigned long end)
+{
+	end = ALIGN(end, PGDIR_SIZE);
+	memcpy(pgd_offset(mm, start), pgd_offset_k(start),
+	       sizeof(pgd_t) * (pgd_index(end) - pgd_index(start)));
+}
+
 void __check_vmalloc_seq(struct mm_struct *mm)
 {
 	int seq;
 
 	do {
-		seq = atomic_read(&init_mm.context.vmalloc_seq);
-		memcpy(pgd_offset(mm, VMALLOC_START),
-		       pgd_offset_k(VMALLOC_START),
-		       sizeof(pgd_t) * (pgd_index(VMALLOC_END) -
-					pgd_index(VMALLOC_START)));
+		seq = atomic_read_acquire(&init_mm.context.vmalloc_seq);
+		memcpy_pgd(mm, VMALLOC_START, VMALLOC_END);
+		if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
+			unsigned long start =
+				arm_kasan_mem_to_shadow(VMALLOC_START);
+			unsigned long end =
+				arm_kasan_mem_to_shadow(VMALLOC_END);
+			memcpy_pgd(mm, start, end);
+		}
 		/*
 		 * Use a store-release so that other CPUs that observe the
 		 * counter's new value are guaranteed to see the results of the

arch/arm/vfp/vfpmodule.c

···
 union vfp_state *vfp_current_hw_state[NR_CPUS];
 
 /*
+ * Claim ownership of the VFP unit.
+ *
+ * The caller may change VFP registers until vfp_state_release() is called.
+ *
+ * local_bh_disable() is used to disable preemption and to disable VFP
+ * processing in softirq context. On PREEMPT_RT kernels local_bh_disable() is
+ * not sufficient because it only serializes soft interrupt related sections
+ * via a local lock, but stays preemptible. Disabling preemption is the right
+ * choice here as bottom half processing is always in thread context on RT
+ * kernels so it implicitly prevents bottom half processing as well.
+ */
+static void vfp_state_hold(void)
+{
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_disable();
+	else
+		preempt_disable();
+}
+
+static void vfp_state_release(void)
+{
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_enable();
+	else
+		preempt_enable();
+}
+
+/*
  * Is 'thread's most up to date state stored in this CPUs hardware?
  * Must be called from non-preemptible context.
  */
···
 /*
  * Process bitmask of exception conditions.
  */
-static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_regs *regs)
+static int vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr)
 {
 	int si_code = 0;
 
···
 
 	if (exceptions == VFP_EXCEPTION_ERROR) {
 		vfp_panic("unhandled bounce", inst);
-		vfp_raise_sigfpe(FPE_FLTINV, regs);
-		return;
+		return FPE_FLTINV;
 	}
 
 	/*
···
 	RAISE(FPSCR_OFC, FPSCR_OFE, FPE_FLTOVF);
 	RAISE(FPSCR_IOC, FPSCR_IOE, FPE_FLTINV);
 
-	if (si_code)
-		vfp_raise_sigfpe(si_code, regs);
+	return si_code;
 }
 
 /*
···
 static void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 {
 	u32 fpscr, orig_fpscr, fpsid, exceptions;
+	int si_code2 = 0;
+	int si_code = 0;
 
 	pr_debug("VFP: bounce: trigger %08x fpexc %08x\n", trigger, fpexc);
 
···
 		 * unallocated VFP instruction but with FPSCR.IXE set and not
 		 * on VFP subarch 1.
 		 */
-		 vfp_raise_exceptions(VFP_EXCEPTION_ERROR, trigger, fpscr, regs);
-		return;
+		si_code = vfp_raise_exceptions(VFP_EXCEPTION_ERROR, trigger, fpscr);
+		goto exit;
 	}
 
 	/*
···
 	 */
 	exceptions = vfp_emulate_instruction(trigger, fpscr, regs);
 	if (exceptions)
-		vfp_raise_exceptions(exceptions, trigger, orig_fpscr, regs);
+		si_code2 = vfp_raise_exceptions(exceptions, trigger, orig_fpscr);
 
 	/*
 	 * If there isn't a second FP instruction, exit now. Note that
 	 * the FPEXC.FP2V bit is valid only if FPEXC.EX is 1.
 	 */
 	if ((fpexc & (FPEXC_EX | FPEXC_FP2V)) != (FPEXC_EX | FPEXC_FP2V))
-		return;
+		goto exit;
 
 	/*
 	 * The barrier() here prevents fpinst2 being read
···
  emulate:
 	exceptions = vfp_emulate_instruction(trigger, orig_fpscr, regs);
 	if (exceptions)
-		vfp_raise_exceptions(exceptions, trigger, orig_fpscr, regs);
+		si_code = vfp_raise_exceptions(exceptions, trigger, orig_fpscr);
+exit:
+	vfp_state_release();
+	if (si_code2)
+		vfp_raise_sigfpe(si_code2, regs);
+	if (si_code)
+		vfp_raise_sigfpe(si_code, regs);
 }
 
 static void vfp_enable(void *unused)
···
  */
 void vfp_sync_hwstate(struct thread_info *thread)
 {
-	unsigned int cpu = get_cpu();
+	vfp_state_hold();
 
-	local_bh_disable();
-
-	if (vfp_state_in_hw(cpu, thread)) {
+	if (vfp_state_in_hw(raw_smp_processor_id(), thread)) {
 		u32 fpexc = fmrx(FPEXC);
 
 		/*
···
 		fmxr(FPEXC, fpexc);
 	}
 
-	local_bh_enable();
-	put_cpu();
+	vfp_state_release();
 }
 
 /* Ensure that the thread reloads the hardware VFP state on the next use. */
···
 	if (!user_mode(regs))
 		return vfp_kmode_exception(regs, trigger);
 
-	local_bh_disable();
+	vfp_state_hold();
 	fpexc = fmrx(FPEXC);
 
 	/*
···
 		 * replay the instruction that trapped.
 		 */
 		fmxr(FPEXC, fpexc);
+		vfp_state_release();
 	} else {
 		/* Check for synchronous or asynchronous exceptions */
 		if (!(fpexc & (FPEXC_EX | FPEXC_DEX))) {
···
 			if (!(fpscr & FPSCR_IXE)) {
 				if (!(fpscr & FPSCR_LENGTH_MASK)) {
 					pr_debug("not VFP\n");
-					local_bh_enable();
+					vfp_state_release();
 					return -ENOEXEC;
 				}
 				fpexc |= FPEXC_DEX;
 			}
 		}
 bounce:		regs->ARM_pc += 4;
+		/* VFP_bounce() will invoke vfp_state_release() */
 		VFP_bounce(trigger, fpexc, regs);
 	}
 
-	local_bh_enable();
 	return 0;
 }
 
···
 	unsigned int cpu;
 	u32 fpexc;
 
-	local_bh_disable();
+	vfp_state_hold();
 
 	/*
 	 * Kernel mode NEON is only allowed outside of hardirq context with
···
 {
 	/* Disable the NEON/VFP unit. */
 	fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
-	local_bh_enable();
+	vfp_state_release();
 }
 EXPORT_SYMBOL(kernel_neon_end);
 

drivers/amba/bus.c

···
 };
 EXPORT_SYMBOL_GPL(amba_bustype);
 
+bool dev_is_amba(const struct device *dev)
+{
+	return dev->bus == &amba_bustype;
+}
+EXPORT_SYMBOL_GPL(dev_is_amba);
+
 static int __init amba_init(void)
 {
 	return bus_register(&amba_bustype);

include/linux/amba/bus.h

···
 #ifdef CONFIG_ARM_AMBA
 int __amba_driver_register(struct amba_driver *, struct module *);
 void amba_driver_unregister(struct amba_driver *);
+bool dev_is_amba(const struct device *dev);
 #else
 static inline int __amba_driver_register(struct amba_driver *drv,
 					 struct module *owner)
···
 }
 static inline void amba_driver_unregister(struct amba_driver *drv)
 {
+}
+static inline bool dev_is_amba(const struct device *dev)
+{
+	return false;
 }
 #endif